#789 by GitHub stars
SpaceZephyr/pm-skills
Marty Cagan 视角顾问。以 Cagan 的产品运营模型和决策方式，分析产品经理面临的立项、 团队、需求与交付问题。蒸馏自《Inspired》《Empowered》《Transformed》及 SVPG 长文， 含 4 个心智模型、7 条决策启发式。 触发词：「Cagan」「卡根」「用 Cagan 的视角」「Cagan 会怎么看」「四大风险」「product model」 「赋能团队」「discovery」「feature team vs product team」。 用户问"这需求该不该做"「团队该怎么组」「怎么做产品发现」时也可触发。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
pm-advisory-suite/pm-advisor-cagan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-advisory-suite/pm-advisor-torres/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-advisory-suite/pm-advisor-yujun/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-advisory-suite/pm-advisory-board/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-advisory-suite/pm-method-build-trap/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-advisory-suite/pm-method-mom-test/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-advisory-suite/pm-method-story-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-analytics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-competitor-deconstructor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-experiment-designer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-image2pencil/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-image2proto/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-master/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-postmortem-writer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-prd-writer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-prioritization-engine/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-review-board/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-roadmap-planner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-survey-designer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-tracking-spec-writer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
pm-url2proto/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
space-image2proto/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
space-url2proto/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
4c486c7a532d → 4c486c7a532d
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4c486c7a532d
No earlier version was observed for comparison.
Heat
5.7- Star growth, last 7 daysAhead of 88% of tracked repositories
- Star growth, last 24 hoursAhead of 86% of tracked repositories
- Rank movement, last 7 daysAhead of 45% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- pm-advisor-cagan
pm-advisory-suite/pm-advisor-cagan - pm-advisor-torres
pm-advisory-suite/pm-advisor-torres - pm-advisor-yujun
pm-advisory-suite/pm-advisor-yujun - pm-advisory-board
pm-advisory-suite/pm-advisory-board - pm-method-build-trap
pm-advisory-suite/pm-method-build-trap - pm-method-mom-test
pm-advisory-suite/pm-method-mom-test - pm-method-story-mapping
pm-advisory-suite/pm-method-story-mapping - pm-analytics
pm-analytics - pm-competitor-deconstructor
pm-competitor-deconstructor - pm-experiment-designer
pm-experiment-designer - pm-image2pencil
pm-image2pencil - pm-image2proto
pm-image2proto - pm-master
pm-master - pm-postmortem-writer
pm-postmortem-writer - pm-prd-writer
pm-prd-writer - pm-prioritization-engine
pm-prioritization-engine - pm-review-board
pm-review-board - pm-roadmap-planner
pm-roadmap-planner - pm-survey-designer
pm-survey-designer - pm-tracking-spec-writer
pm-tracking-spec-writer - pm-url2proto
pm-url2proto - space-image2proto
space-image2proto - web-prototype
space-url2proto
How it works
pm-advisor-cagan
When your agent uses it
Marty Cagan 视角顾问。以 Cagan 的产品运营模型和决策方式，分析产品经理面临的立项、 团队、需求与交付问题。蒸馏自《Inspired》《Empowered》《Transformed》及 SVPG 长文， 含 4 个心智模型、7 条决策启发式。 触发词：「Cagan」「卡根」「用 Cagan 的视角」「Cagan 会怎么看」「四大风险」「product model」 「赋能团队」「discovery」「feature team vs product team」。 用户问"这需求该不该做"「团队该怎么组」「怎么做产品发现」时也可触发。
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
2,864 tokensWhen the skill is activated
Reference documents
827 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ⚡ 角色扮演规则
- 回答工作流
- 身份卡
- 核心心智模型（4 个，均通过三重验证）
- 决策启发式（7 条）
- 表达 DNA
- 价值观与反模式
- 内在张力
- 诚实边界
- 调研来源
Files
SKILL.mdcore10,536 bytesreferences/research.mddoc2,735 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-advisor-torres
When your agent uses it
Teresa Torres 视角顾问。以 Torres 的持续发现（Continuous Discovery）方法和决策方式， 分析产品经理的用户发现、机会梳理、方案生成与假设验证问题。 蒸馏自《Continuous Discovery Habits》及 Product Talk 长文，含 4 个心智模型、7 条决策启发式。 触发词：「Teresa Torres」「Torres」「用 Torres 的视角」「持续发现」「机会解决方案树」 「opportunity solution tree」「assumption test」「每周用户触点」「outcome」。 用户问"怎么做用户发现"「需求怎么拆成机会」「怎么验证假设」时也可触发。
What it loads into context
Frontmatter
167 tokensAlways available to the agent
SKILL.md
2,782 tokensWhen the skill is activated
Reference documents
692 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ⚡ 角色扮演规则
- 回答工作流
- 身份卡
- 核心心智模型（4 个，均通过三重验证）
- 决策启发式（7 条）
- 表达 DNA
- 价值观与反模式
- 内在张力
- 诚实边界
- 调研来源
Files
SKILL.mdcore10,256 bytesreferences/research.mddoc2,246 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-advisor-yujun
When your agent uses it
俞军视角顾问。以俞军的用户价值理论和交易模型，分析产品的价值判断、用户迁移、 取舍决策问题。蒸馏自《俞军产品方法论》及其公开分享，含 4 个心智模型、6 条决策启发式。 触发词：「俞军」「用俞军的视角」「俞军会怎么看」「用户价值公式」「交易模型」 「替换成本」「决策效用」「产品经理是决策者」。 用户问"这功能对用户价值多大"「用户为什么不迁移过来」「这个取舍怎么定」时也可触发。
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
2,890 tokensWhen the skill is activated
Reference documents
698 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ⚡ 角色扮演规则
- 回答工作流
- 身份卡
- 核心心智模型（4 个，均通过三重验证）
- 决策启发式（6 条）
- 表达 DNA
- 价值观与反模式
- 内在张力
- 诚实边界
- 调研来源
Files
SKILL.mdcore10,308 bytesreferences/research.mddoc2,225 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-advisory-board
When your agent uses it
产品经理专家顾问团总控。成员：Marty Cagan、Teresa Torres、俞军（专家视角）+ 《The Mom Test》《User Story Mapping》《Escaping the Build Trap》（方法论）。 能力：(1)根据问题自动推荐合适的专家/方法论 (2)召开多专家评审会，输出共识/分歧/综合结论。 面向"提升产出质量"：从需求真伪、方案结构，到成效导向，帮 PM 把产出做扎实。 触发词：「产品顾问团」「PM 顾问团」「专家评审」「让专家们看看这个需求/方案」「开评审会」。
What it loads into context
Frontmatter
168 tokensAlways available to the agent
SKILL.md
2,097 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 成员名册
- 模式一：路由（默认）
- 模式二：评审会
- 分歧地图（预置）
- 成员未安装时的降级
- 顾问团的诚实边界
Files
SKILL.mdcore7,364 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-method-build-trap
When your agent uses it
《Escaping the Build Trap》方法论。把 Melissa Perri 的成效导向产品管理转化为可执行框架， 用于：判断团队是否陷入"功能工厂"、把战略拆成可落地的成效、用产品 kata 系统性验证。 每条规则标注原书章节，可追溯。 触发词：「Escaping the Build Trap」「跳出功能陷阱」「功能工厂」「build trap」「outcome over output」 「product kata」「产品运营模型」「战略部署」及"忙着做功能但不知道有没有用"类场景。
What it loads into context
Frontmatter
147 tokensAlways available to the agent
SKILL.md
1,778 tokensWhen the skill is activated
Reference documents
480 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 什么时候用我
- 核心框架
- 决策规则（来源标注）
- 检查清单：跳出功能陷阱（综合全书）
- 反模式（书中明确警告）
- 边界声明
- 工作流
Files
SKILL.mdcore6,457 bytesreferences/framework.mddoc1,754 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-method-mom-test
When your agent uses it
《The Mom Test》方法论。把 Rob Fitzpatrick 的用户访谈框架转化为可执行规则， 用于：设计不被善意误导的用户访谈、从对话中提取真实信号、判断一个需求是真是假。 每条规则标注原书章节，可追溯。 触发词：「Mom Test」「妈妈测试」「用户访谈」「客户访谈」「怎么问用户」「需求验证」 「访谈提纲」及"用户说想要但不确定真假"类场景。
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
1,907 tokensWhen the skill is activated
Reference documents
472 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 什么时候用我
- 核心框架
- 决策规则（来源标注）
- 检查清单：一次访谈的信号过滤（综合第 2、3、5 章）
- 反模式（书中明确警告）
- 边界声明
- 工作流
Files
SKILL.mdcore6,493 bytesreferences/framework.mddoc1,608 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-method-story-mapping
When your agent uses it
《User Story Mapping》方法论。把 Jeff Patton 的用户故事地图转化为可执行框架， 用于：把需求拆成能沟通的整体骨架、切出最小可用的发布切片、避免扁平待办清单。 每条规则标注原书章节，可追溯。 触发词：「User Story Mapping」「用户故事地图」「故事地图」「需求拆解」「MVP 切片」 「backbone」「walking skeleton」「怎么写用户故事」及"需求太碎/PRD 说不清全貌"类场景。
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
1,815 tokensWhen the skill is activated
Reference documents
471 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 什么时候用我
- 核心框架
- 决策规则（来源标注）
- 检查清单：一张健康的故事地图（综合第 5、6 章）
- 反模式（书中明确警告）
- 边界声明
- 工作流
Files
SKILL.mdcore6,211 bytesreferences/framework.mddoc1,624 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-analytics
When your agent uses it
从数据现象出发，生成可执行的产品决策建议，并以可视化 HTML 报告输出。当用户说"分析一下这组数据"、"这个指标为什么跌了"、"帮我做个留存分析"、"用户流失原因是什么"、"看看漏斗哪一步掉了"、"给我出个数据分析报告"时触发。 也适用于：用户上传了 CSV/Excel 数据文件并要求分析洞察；用户提供了 SQL 查询结果要求解读；用户要求做指标拆解、归因分析、分群对比、A/B 实验分析；用户提到"指标树"、"漏斗"、"留存"、"转化率"、"DAU 下降"、"分群"、"归因"等数据分析关键词。 不适用于：纯 BI 看板搭建（用 xlsx）、纯 SQL 编写（直接写）、纯数据清洗（直接写脚本）。
What it loads into context
Frontmatter
226 tokensAlways available to the agent
SKILL.md
5,671 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的角色
- 核心工作流
- 步骤一：明确分析目标（Align）
- 步骤二：数据体检（Health Check）
- 步骤三：指标拆解（Decompose）
- 步骤四：现象定位（Locate）
- 步骤五：假设推断（Hypothesize）
- 步骤六：行动建议（Act）
- HTML 报告输出规范
- 兜底策略
- 设计文档面板（每个报告自动内嵌）
- 上下游衔接
Files
.DS_Storeasset6,148 bytesSKILL.mdcore19,032 bytesassets/report-template.htmlasset18,974 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-competitor-deconstructor
When your agent uses it
按策略/功能/体验/增长四个维度结构化拆解竞品，输出可借鉴点、不可抄点与差异化建议。当用户说"竞品分析"、"竞品拆解"、"帮我分析竞品"、"看看这几个竞品"、"competitor analysis"、"和竞品比一下"、"对标分析"、"差异化怎么做"， 或者用户给出了一份竞品名单并要求系统化分析时，使用这个 Skill。 也适用于：用户上传了竞品截图/链接/体验报告并要求结构化拆解；用户要求对比自己产品与竞品的差距；用户想找差异化切入点。 不适用于：纯需求文档撰写（用 pm-prd-writer）、纯优先级排序（用 pm-prioritization-engine）、纯用户调研设计（用 pm-survey-designer）。
What it loads into context
Frontmatter
224 tokensAlways available to the agent
SKILL.md
3,332 tokensWhen the skill is activated
Reference documents
1,843 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的角色
- 核心工作流
- 阶段一：信息采集与确认（Intake）
- 阶段二：四维结构化拆解（Deconstruct）
- 阶段三：横向对比矩阵（Compare）
- 阶段四：策略建议输出（Recommend）
- 质量检查清单
- 失败兜底策略
- 参考文件
- 上下游衔接
Files
SKILL.mdcore11,463 bytesreferences/analysis-framework.mddoc4,410 bytesreferences/data-sources.mddoc1,928 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-experiment-designer
When your agent uses it
A/B 实验设计 Skill。从实验目标出发，输出完整的实验方案（假设、分组、指标体系、样本量估算、止损规则、判定规则）。 触发条件：用户提到"A/B 测试"、"AB 实验"、"实验设计"、"对照实验"、"分流实验"、"灰度方案"、"实验方案"、"样本量计算"、"显著性检验"、"实验评估"、"p值"、"置信区间"、"MDE"、"统计功效"、"实验周期"、"止损规则"等关键词。 也适用于：用户提供了实验目标/可改动点/数据量级/周期限制要求产出实验方案；用户要求评估现有实验设计是否合理；用户要求制定实验判定标准和决策规则。 典型输入：实验目标 + 可改动点 + 当前数据量级 + 可接受实验周期。 不适用于：纯数据分析（用 pm-analytics）、纯埋点设计（用 tracking-spec-writer）、纯PRD写作（用 pm-prd-writer）。
What it loads into context
Frontmatter
275 tokensAlways available to the agent
SKILL.md
5,783 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的角色
- 核心工作流
- 步骤一：明确实验假设
- 步骤二：设计实验单元
- 步骤三：设定指标体系
- 步骤四：样本量估算
- 步骤五：判定与止损规则
- 输出格式
- 设计文档面板（每个方案自动内嵌）
- 兜底策略
- 质量检查项
- 上下游衔接
Files
.DS_Storeasset6,148 bytesSKILL.mdcore19,133 bytesassets/experiment-template.htmlasset25,742 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-image2pencil
When your agent uses it
将截图/设计稿复刻为 Pencil .pen 设计，并在同一画布旁输出结构化设计文档。用户提到“按图复刻”“照着截图画页面”“image to pencil”“做一个一模一样的页面”“根据这张图做设计稿”“输出设计图和文档”时使用本 Skill。 也适用于：用户要求修改已有 .pen 页面、追加右侧设计文档、做像素级对齐、根据多张截图整合一套页面。 本 Skill 必须调用 pencil MCP 工具完成读取、绘制和截图校验；若信息不全，先向用户索取缺失信息再开始绘制。
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
1,438 tokensWhen the skill is activated
Reference documents
646 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- 对话流程（严格执行）
- 输出标准
- 参考文件
- 上下游衔接
Files
SKILL.mdcore5,182 bytesreferences/design-doc-template.mddoc1,008 bytesreferences/intake-checklist.mddoc1,120 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-image2proto
When your agent uses it
Screenshot-to-HTML prototype generator with iterative refinement and learning memory. Use this skill whenever the user provides a screenshot, mockup, wireframe, or image of any UI and wants it reproduced as a working HTML prototype — or when they want to modify an existing prototype they previously generated. Also triggers on: "照这个做原型", "参考这个图", "把这个页面画出来", "this UI needs to be prototyped", "replicate this design", "convert this mockup to HTML", "帮我出个原型", "根据截图输出 HTML", or any image attachment combined with requests like "输出 HTML", "做成页面", "帮我实现". Even if the user just sends a screenshot with a brief instruction like "加一个字段" or "这个也一样", this skill applies — it means they want you to modify or replicate the UI shown. When in doubt, if there's a UI screenshot in the conversation, use this skill.
What it loads into context
Frontmatter
209 tokensAlways available to the agent
SKILL.md
3,684 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First launch: onboarding
- Core workflow
- Design system reference
- Common component patterns
- Flowchart / Mermaid diagrams
- Quality checklist
- Handling "输出设计说明"
- 上下游衔接
Files
SKILL.mdcore15,524 bytesSKILL.mdcore15,524 bytesreferences/design_system.jsonasset186 bytesreferences/learning_log.jsonlasset0 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-master
When your agent uses it
产品经理 Skill 库全局总控。管理 20 个 PM Skill：13 个执行工具（PRD、评审、优先级、路线图、数据分析、实验、埋点、问卷、竞品、复盘、原型×3）+ 7 个专家顾问团（Cagan、Torres、俞军、Mom Test、Story Mapping、Build Trap 及其总控）。 能力：(1)根据用户描述的问题自动路由到最合适的 Skill (2)编排多 Skill 工作流链路，把上一步产出接力给下一步 (3)判断类问题转交 pm-advisory-board 组织专家评审。 触发词：「pm-master」「产品总控」「我该用哪个 Skill」「帮我推进这个需求」「从头到尾走一遍」「完整链路」， 或者用户描述了一个产品工作场景但没有指明用哪个 Skill、或一个任务明显需要多个 Skill 接力完成时，优先使用本 Skill。
What it loads into context
Frontmatter
234 tokensAlways available to the agent
SKILL.md
2,299 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 成员名册
- 第一步：问题分诊
- 第二步：单点路由表
- 第三步：预置工作流链路
- 澄清规则
- 降级策略
- 诚实边界
Files
SKILL.mdcore7,719 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-postmortem-writer
When your agent uses it
生成结构化的上线复盘报告，包含目标达成、偏差原因、经验沉淀和后续行动项（含责任归因和改进 owner）。当用户说"写复盘""上线复盘""项目复盘""复盘报告""postmortem""版本回顾""迭代总结""上线总结"， 或者用户提供了上线数据/过程记录/问题清单并要求结构化总结时，使用这个 Skill。 也适用于：事故复盘（P0/P1 事故后的 RCA 报告）、OKR 复盘、季度复盘、A/B 实验复盘。 不适用于：纯需求撰写（用 pm-prd-writer）、纯优先级排序（用 pm-prioritization-engine）、周报日报（用 status-report）。
What it loads into context
Frontmatter
193 tokensAlways available to the agent
SKILL.md
3,750 tokensWhen the skill is activated
Reference documents
1,764 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的角色
- 核心工作流
- 阶段一：信息采集（Intake）
- 阶段二：目标对照结果（Review）
- 阶段三：偏差归因（Root Cause）
- 阶段四：经验沉淀（Lessons Learned）
- 阶段五：行动项输出（Action Items）
- 完整复盘报告结构
- 质量检查清单
- 不同复盘场景的裁剪建议
- 失败兜底策略
- 参考文件
- 上下游衔接
Files
SKILL.mdcore12,948 bytesreferences/root-cause-methods.mddoc5,559 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-prd-writer
When your agent uses it
把模糊需求转化为可评审的产品需求文档（PRD）。当用户说"写个需求文档"、"帮我出PRD"、"这个功能怎么写需求"、"我有个想法想落地"、"把这个需求整理成文档"、"需求评审要用的PRD"，或者用户描述了一段功能但没有结构化时，使用这个 Skill。 也适用于：用户上传了原始需求描述/会议纪要/聊天截图并要求整理成PRD；用户说"PRD"、"产品需求"、"需求文档"、"功能说明书"等关键词；用户要求对已有PRD进行补全、优化、查漏补缺。 不适用于：纯技术方案设计（用 architecture）、纯 UI 稿标注（用 design-handoff）、项目管理类文档（用 status-report）。
What it loads into context
Frontmatter
212 tokensAlways available to the agent
SKILL.md
3,672 tokensWhen the skill is activated
Reference documents
2,685 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的角色
- 核心工作流
- 阶段零：需求体检（写之前先问该不该写）
- 阶段一：需求澄清（Clarify）
- 阶段二：结构化输出（Structure）
- 阶段三：自动补漏（Enrich）
- 阶段四：验收输出（Deliver）
- 质量检查清单
- 失败兜底策略
- 输出格式
- 上下游衔接
Files
SKILL.mdcore12,891 bytesreferences/prd-template.mddoc8,944 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-prioritization-engine
When your agent uses it
对需求/功能/项目进行多维度优先级排序，输出版本排期建议。当用户说"帮我排优先级"、"这些需求怎么排"、"用 RICE 打分"、"ICE 评分"、"Kano 分析"、"成本收益分析"、"功能排期"、"路线图规划"、"哪些先做哪些后做"、"版本规划"， 或者用户列出了一批需求/功能/项目并需要决策顺序时，使用这个 Skill。 也适用于：用户想比较多个优先级模型的结果；用户对当前路线图有疑问想重新评估；资源有限需要砍需求；用户提到"RICE"、"ICE"、"Kano"、"优先级矩阵"等专业术语。 不适用于：纯项目管理（排期甘特图）、纯需求文档撰写（用 pm-prd-writer）、纯用户调研设计（用 pm-survey-designer）。
What it loads into context
Frontmatter
239 tokensAlways available to the agent
SKILL.md
3,948 tokensWhen the skill is activated
Reference documents
3,743 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的角色
- 核心工作流
- 阶段一：需求池整理（Intake）
- 阶段二：模型选择（Model Selection）
- 阶段三：多模型评分（Scoring）
- 阶段四：权重校准（Calibration）
- 阶段五：路线图输出（Roadmap）
- 质量检查清单
- 失败兜底策略
- 参考文件
- 上下游衔接
Files
SKILL.mdcore13,935 bytesreferences/kano-analysis.mddoc5,319 bytesreferences/scoring-models.mddoc7,069 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-review-board
When your agent uses it
模拟多角色 PRD/原型评审会，从产品、研发、测试、设计、运营、法务六大视角给出评审结论。当用户说"帮我评审一下这个 PRD"、"看看这个需求有没有问题"、"模拟评审会"、"review 一下这个文档"、"这个需求能不能过评审"、"帮我查漏补缺"时触发。 也适用于：用户上传了 PRD、需求文档、原型截图、功能说明并要求检查；用户提到"评审"、"review"、"过会"、"需求评审"、"方案评审"等关键词；用户要求从研发或测试视角看需求是否可行。 不适用于：写 PRD（用 pm-prd-writer）、纯代码审查（用 code-review）、纯设计走查（用 design-critique）。
What it loads into context
Frontmatter
212 tokensAlways available to the agent
SKILL.md
3,924 tokensWhen the skill is activated
Reference documents
1,708 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的角色
- 评审严格度（先定档位再开评）
- 评审角色
- 工作流
- 步骤一：材料通读
- 步骤二：多角色并行审阅
- 步骤三：冲突归并
- 步骤四：风险分级
- 步骤五：输出评审结论
- 总体判定规则
- 工作量评估说明
- 重大评审：并行子代理模式
- 兜底策略
- 上下游衔接
Files
SKILL.mdcore14,196 bytesreferences/review-checklist.mddoc5,963 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-roadmap-planner
When your agent uses it
版本规划与路线图设计 Skill。从季度目标、团队产能、依赖方信息出发，输出可执行的版本路线图（里程碑、依赖风险、缓冲策略、每阶段成功指标）。 触发条件：用户提到"路线图"、"版本规划"、"roadmap"、"里程碑"、"季度计划"、"迭代规划"、"版本排期"、"项目排期"、"依赖梳理"、"风险预案"、"缓冲方案"、"迭代计划"、"sprint规划"、"release plan"、"OKR拆解"等关键词。 也适用于：用户提供季度目标/团队产能/依赖信息要求排期；用户要求将战略目标拆解为可执行的里程碑；用户要求评估项目风险和缓冲方案；用户要求制定跨团队协作的版本计划。 典型输入：季度目标 + 团队产能 + 依赖方信息 + 约束条件。 不适用于：每日站会（直接沟通）、单个需求设计（用 pm-prd-writer）、数据分析（用 pm-analytics）。
What it loads into context
Frontmatter
279 tokensAlways available to the agent
SKILL.md
5,332 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的角色
- 核心工作流
- 步骤一：目标对齐
- 步骤二：能力拆分
- 步骤三：里程碑编排
- 步骤四：风险与缓冲
- 每阶段成功指标
- 输出格式
- 设计文档面板（每个方案自动内嵌）
- 兜底策略
- 质量检查项
- 上下游衔接
Files
.DS_Storeasset6,148 bytesSKILL.mdcore16,794 bytesassets/roadmap-template.htmlasset24,514 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-survey-designer
When your agent uses it
设计高质量调研问卷。当用户说"设计问卷"、"做个调研"、"帮我出份问卷"、"用户调研"、"满意度调查"、"NPS问卷"、"市场调研"、"需求调研"、"问卷设计"、"survey design"， 或者用户描述了一个调研目标但还没有结构化的问卷时，使用这个 Skill。 也适用于：用户上传了已有问卷要求优化/查偏差/补充题目；用户说"帮我检查这份问卷有没有问题"；用户需要设计 A/B 测试问卷、焦点小组访谈提纲、NPS/CSAT/CES 调查； 用户提到"诱导题"、"双重问题"、"问卷偏差"等专业术语。 不适用于：纯数据分析（用 pm-analytics）、纯用户访谈记录整理（直接整理即可）、纯产品需求文档（用 pm-prd-writer）。
What it loads into context
Frontmatter
244 tokensAlways available to the agent
SKILL.md
4,103 tokensWhen the skill is activated
Reference documents
3,615 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的角色
- 核心工作流
- 阶段一：目标拆解（Decompose）
- 阶段二：题目设计（Design）
- 阶段三：偏差审查（Audit）
- 阶段四：样本与发放（Sample & Distribute）
- 阶段五：分析框架（Analysis Framework）
- 最终交付
- 质量检查清单
- 失败兜底策略
- 上下游衔接
Files
SKILL.mdcore13,672 bytesreferences/bias-checklist.mddoc5,782 bytesreferences/question-types.mddoc5,624 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-tracking-spec-writer
When your agent uses it
埋点与指标设计方案生成器。从产品需求/核心链路出发，输出完整的埋点方案文档（事件、字段、触发时机、口径说明、QA 校验清单）。 触发条件：用户提到"埋点"、"tracking"、"事件设计"、"数据采集"、"上报方案"、"埋点方案"、"事件规范"、"字段设计"、"指标口径"、"数据验收"、"QA校验"等关键词。 也适用于：用户提供产品PRD/需求文档要求产出埋点方案；用户提供核心用户链路要求拆解事件；用户要求规范化事件命名或字段定义；用户要求设计数据验收方案。 典型输入：事件命名规范 + 字段字典 + 核心链路描述/流程图。 不适用于：纯数据分析（用 pm-analytics）、纯BI看板搭建、纯SQL查询编写。
What it loads into context
Frontmatter
240 tokensAlways available to the agent
SKILL.md
5,811 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的角色
- 核心工作流
- 步骤一：理解业务链路
- 步骤二：链路拆事件
- 步骤三：事件字段定义
- 步骤四：命名规范校验
- 步骤五：数据验收计划
- 输出格式
- 设计文档面板（每个方案自动内嵌）
- 兜底策略
- 质量检查项
- 上下游衔接
Files
.DS_Storeasset6,148 bytesSKILL.mdcore19,935 bytesassets/spec-template.htmlasset19,850 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpm-url2proto
When your agent uses it
Clone live web pages into a local Next.js + Tailwind CSS project for rapid prototyping. Use this skill whenever a user shares a URL or screenshot and wants to replicate, redesign, or iterate on that page locally — whether they say "clone this site", "make a prototype based on this page", "recreate this UI", "build something that looks like this", or simply paste a link and ask you to turn it into code. Also trigger when the user wants to add new pages, modify existing pages, or extend a prototype project that was previously created by this skill. Even if the user just says "I want to build a page like X" with a reference link or image, this skill applies.
What it loads into context
Frontmatter
155 tokensAlways available to the agent
SKILL.md
2,776 tokensWhen the skill is activated
Reference documents
2,792 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Conversation flow
- Phase 1: Capture the source page
- Phase 2: Build the Next.js project
- Phase 3: Verify and compare
- Phase 4: Hand off
- Extending an existing prototype
- Design Document System
- Important principles
- 上下游衔接
Files
.DS_Storeasset6,148 bytesSKILL.mdcore11,515 bytesSKILL.mdcore11,515 bytesSKILL.mdcore11,515 bytesSKILL.mdcore11,515 bytesevals/evals.jsonasset1,245 bytesreferences/extraction-scripts.mddoc7,669 bytesreferences/project-scaffold.mddoc3,070 bytesweb-prototype-skill-intro.htmlasset30,611 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubspace-image2proto
When your agent uses it
Screenshot-to-HTML prototype generator with iterative refinement and learning memory. Use this skill whenever the user provides a screenshot, mockup, wireframe, or image of any UI and wants it reproduced as a working HTML prototype — or when they want to modify an existing prototype they previously generated. Also triggers on: "照这个做原型", "参考这个图", "把这个页面画出来", "this UI needs to be prototyped", "replicate this design", "convert this mockup to HTML", "帮我出个原型", "根据截图输出 HTML", or any image attachment combined with requests like "输出 HTML", "做成页面", "帮我实现". Even if the user just sends a screenshot with a brief instruction like "加一个字段" or "这个也一样", this skill applies — it means they want you to modify or replicate the UI shown. When in doubt, if there's a UI screenshot in the conversation, use this skill.
What it loads into context
Frontmatter
209 tokensAlways available to the agent
SKILL.md
3,548 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First launch: onboarding
- Core workflow
- Design system reference
- Common component patterns
- Flowchart / Mermaid diagrams
- Quality checklist
- Handling "输出设计说明"
Files
SKILL.mdcore15,056 bytesSKILL.mdcore15,056 bytesreferences/design_system.jsonasset186 bytesreferences/learning_log.jsonlasset0 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubweb-prototype
When your agent uses it
Clone live web pages into a local Next.js + Tailwind CSS project for rapid prototyping. Use this skill whenever a user shares a URL or screenshot and wants to replicate, redesign, or iterate on that page locally — whether they say "clone this site", "make a prototype based on this page", "recreate this UI", "build something that looks like this", or simply paste a link and ask you to turn it into code. Also trigger when the user wants to add new pages, modify existing pages, or extend a prototype project that was previously created by this skill. Even if the user just says "I want to build a page like X" with a reference link or image, this skill applies.
What it loads into context
Frontmatter
154 tokensAlways available to the agent
SKILL.md
2,657 tokensWhen the skill is activated
Reference documents
2,792 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Conversation flow
- Phase 1: Capture the source page
- Phase 2: Build the Next.js project
- Phase 3: Verify and compare
- Phase 4: Hand off
- Extending an existing prototype
- Design Document System
- Important principles
Files
.DS_Storeasset6,148 bytesSKILL.mdcore11,087 bytesSKILL.mdcore11,087 bytesSKILL.mdcore11,087 bytesSKILL.mdcore11,087 bytesevals/evals.jsonasset1,245 bytesreferences/extraction-scripts.mddoc7,669 bytesreferences/project-scaffold.mddoc3,070 bytesweb-prototype-skill-intro.htmlasset30,611 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- pm-advisor-cagan
- pm-advisor-torres
- pm-advisor-yujun
- pm-advisory-board
- pm-method-build-trap
- pm-method-mom-test
- pm-method-story-mapping
- pm-analytics
- pm-competitor-deconstructor
- pm-experiment-designer
- pm-image2pencil
- pm-image2proto
- pm-master
- pm-postmortem-writer
- pm-prd-writer
- pm-prioritization-engine
- pm-review-board
- pm-roadmap-planner
- pm-survey-designer
- pm-tracking-spec-writer
- pm-url2proto
- space-image2proto
- web-prototype
Repository facts
- License
- No license detected
- Created
- Mar 28, 2026
- Last pushed
- Jul 9, 2026
- Forks
- 221
- Open issues
- 4
- Project activity
- Slowing
Rank over the last 12 weeks
Now #789 · best #576 · down 105 in 30 days
- #778 on Oct 30
- #782 on Oct 31
- #784 on Nov 1
- #786 on Nov 2
- #791 from Nov 3 to Nov 4
- #789 since Nov 5
70 earlier periods
- #606 on Aug 2
- #596 on Aug 7
- #591 on Aug 8
- #597 on Aug 9
- #628 on Aug 10
- #632 on Aug 11
- #631 on Aug 12
- #632 on Aug 13
- #627 on Aug 14
- #621 on Aug 16
- #630 on Aug 17
- #644 on Aug 18
- #627 on Aug 19
- #624 on Aug 20
- #630 on Aug 21
- #582 on Aug 22
- #607 on Aug 23
- #610 on Aug 24
- #616 on Aug 25
- #604 on Aug 26
- #612 on Aug 27
- #630 on Aug 28
- #589 from Aug 29 to Aug 30
- #612 on Aug 31
- #610 on Sep 1
- #600 on Sep 2
- #597 on Sep 3
- #578 on Sep 4
- #576 on Sep 5
- #588 on Sep 6
- #596 on Sep 7
- #613 on Sep 8
- #603 on Sep 9
- #605 on Sep 10
- #595 on Sep 11
- #593 on Sep 13
- #613 on Sep 14
- #608 on Sep 15
- #621 on Sep 16
- #618 on Sep 17
- #619 on Sep 18
- #597 on Sep 19
- #609 on Sep 20
- #621 on Sep 21
- #639 on Sep 22
- #634 on Sep 23
- #606 on Sep 25
- #629 on Sep 27
- #634 on Sep 28
- #666 on Sep 29
- #648 on Sep 30
- #612 on Oct 3
- #637 on Oct 5
- #650 on Oct 7
- #684 on Oct 8
- #662 on Oct 9
- #655 on Oct 10
- #648 on Oct 11
- #666 on Oct 12
- #663 on Oct 13
- #677 on Oct 14
- #667 on Oct 15
- #678 on Oct 16
- #685 on Oct 19
- #697 on Oct 20
- #702 on Oct 21
- #682 on Oct 22
- #763 on Oct 25
- #773 on Oct 28
- #776 on Oct 29
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 3, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 8 notes
pm-image2proto/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedpm-url2proto/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedpm-url2proto/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedpm-url2proto/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedspace-image2proto/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedspace-url2proto/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedspace-url2proto/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedspace-url2proto/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 29 network referencesin 6 files: pm-url2proto/evals/evals.json:4 space-url2proto/evals/evals.json:4 pm-analytics/assets/report-template.html:5 and 3 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 29 signals by file
pm-analytics/SKILL.md
pm-analytics/assets/report-template.html
- Network accessline 5
<meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>{{REPORT_TITLE}} - 数据分析报告</title> <script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.min.js"></script> - Network accessline 6
<title>{{REPORT_TITLE}} - 数据分析报告</title> <script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.min.js"></script> <style> - Network accessline 7
<script src="https://cdnjs.cloudflare.com/ajax/libs/Chart.js/4.4.1/chart.umd.min.js"></script>
pm-image2proto/SKILL.md
- Network accessline 268
</div> </div> <script src="https://cdnjs.cloudflare.com/ajax/libs/mermaid/10.9.0/mermaid.min.js"></script> - Network accessline 269
</div> <script src="https://cdnjs.cloudflare.com/ajax/libs/mermaid/10.9.0/mermaid.min.js"></script> <script>mermaid.initialize({...});</script> - Network accessline 270
<script src="https://cdnjs.cloudflare.com/ajax/libs/mermaid/10.9.0/mermaid.min.js"></script>
pm-url2proto/evals/evals.json
- Network accessline 4
{ "id": 1, "prompt": "帮我把这个页面克隆成本地项目: https://stripe.com/payments — 我想基于它做一个自己的支付产品介绍页原型", - Network accessline 5
"id": 1, "prompt": "帮我把这个页面克隆成本地项目: https://stripe.com/payments — 我想基于它做一个自己的支付产品介绍页原型", "expected_output": "一个可运行的 Next.js + Tailwind CSS 项目，页面布局、配色、字体和间距高度还原 Stripe Payments 页面，包含 Header、Hero、功能模块和 Footer 等组件", - Network accessline 6
"prompt": "帮我把这个页面克隆成本地项目: https://stripe.com/payments — 我想基于它做一个自己的支付产品介绍页原型", - Network accessline 10
{ "id": 2, "prompt": "我想做一个类似 Linear 首页的原型，链接是 https://linear.app — 帮我把它的首页样式抓下来搭成本地 Next.js 项目", - Network accessline 11
"id": 2, "prompt": "我想做一个类似 Linear 首页的原型，链接是 https://linear.app — 帮我把它的首页样式抓下来搭成本地 Next.js 项目", "expected_output": "一个还原 Linear 首页视觉风格的 Next.js 项目，暗色主题、动效区域用静态占位、组件结构清晰可编辑", - Network accessline 12
"prompt": "我想做一个类似 Linear 首页的原型，链接是 https://linear.app — 帮我把它的首页样式抓下来搭成本地 Next.js 项目", - Network accessline 16
{ "id": 3, "prompt": "这是一个我们的内部工具: https://vercel.com/dashboard — 帮我克隆这个 dashboard 页面的布局和样式，我想用来做一个新的后台管理原型", - Network accessline 17
"id": 3, "prompt": "这是一个我们的内部工具: https://vercel.com/dashboard — 帮我克隆这个 dashboard 页面的布局和样式，我想用来做一个新的后台管理原型", "expected_output": "一个模仿 Vercel Dashboard 布局的 Next.js 项目，包含侧边栏/顶栏导航、内容区、卡片组件等，样式与原站尽量一致", - Network accessline 18
"prompt": "这是一个我们的内部工具: https://vercel.com/dashboard — 帮我克隆这个 dashboard 页面的布局和样式，我想用来做一个新的后台管理原型",
space-image2proto/SKILL.md
- Network accessline 268
</div> </div> <script src="https://cdnjs.cloudflare.com/ajax/libs/mermaid/10.9.0/mermaid.min.js"></script> - Network accessline 269
</div> <script src="https://cdnjs.cloudflare.com/ajax/libs/mermaid/10.9.0/mermaid.min.js"></script> <script>mermaid.initialize({...});</script> - Network accessline 270
<script src="https://cdnjs.cloudflare.com/ajax/libs/mermaid/10.9.0/mermaid.min.js"></script>
space-url2proto/evals/evals.json
- Network accessline 4
{ "id": 1, "prompt": "帮我把这个页面克隆成本地项目: https://stripe.com/payments — 我想基于它做一个自己的支付产品介绍页原型", - Network accessline 5
"id": 1, "prompt": "帮我把这个页面克隆成本地项目: https://stripe.com/payments — 我想基于它做一个自己的支付产品介绍页原型", "expected_output": "一个可运行的 Next.js + Tailwind CSS 项目，页面布局、配色、字体和间距高度还原 Stripe Payments 页面，包含 Header、Hero、功能模块和 Footer 等组件", - Network accessline 6
"prompt": "帮我把这个页面克隆成本地项目: https://stripe.com/payments — 我想基于它做一个自己的支付产品介绍页原型", - Network accessline 10
{ "id": 2, "prompt": "我想做一个类似 Linear 首页的原型，链接是 https://linear.app — 帮我把它的首页样式抓下来搭成本地 Next.js 项目", - Network accessline 11
"id": 2, "prompt": "我想做一个类似 Linear 首页的原型，链接是 https://linear.app — 帮我把它的首页样式抓下来搭成本地 Next.js 项目", "expected_output": "一个还原 Linear 首页视觉风格的 Next.js 项目，暗色主题、动效区域用静态占位、组件结构清晰可编辑", - Network accessline 12
"prompt": "我想做一个类似 Linear 首页的原型，链接是 https://linear.app — 帮我把它的首页样式抓下来搭成本地 Next.js 项目", - Network accessline 16
{ "id": 3, "prompt": "这是一个我们的内部工具: https://vercel.com/dashboard — 帮我克隆这个 dashboard 页面的布局和样式，我想用来做一个新的后台管理原型", - Network accessline 17
"id": 3, "prompt": "这是一个我们的内部工具: https://vercel.com/dashboard — 帮我克隆这个 dashboard 页面的布局和样式，我想用来做一个新的后台管理原型", "expected_output": "一个模仿 Vercel Dashboard 布局的 Next.js 项目，包含侧边栏/顶栏导航、内容区、卡片组件等，样式与原站尽量一致", - Network accessline 18
"prompt": "这是一个我们的内部工具: https://vercel.com/dashboard — 帮我克隆这个 dashboard 页面的布局和样式，我想用来做一个新的后台管理原型",
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md pm-advisory-suite/pm-advisor-cagan/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md pm-advisory-suite/pm-advisor-cagan/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md pm-advisory-suite/pm-advisor-cagan/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md pm-advisory-suite/pm-advisor-cagan/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md pm-advisory-suite/pm-advisor-cagan/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md pm-advisory-suite/pm-advisor-cagan/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/spacezephyr-pm-skills/)